Participle-network-based word alignment fusion method for computer-aided Chinese-to-English translation

A fusion method and word alignment technology, which is applied in computing, special data processing applications, instruments, etc., can solve problems such as lack, achieve robustness in the word alignment process, improve the quality of word alignment and machine translation, and improve performance

Inactive Publication Date: 2011-09-21
NANJING UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology helps align two languages with one another without having them mixed up together during their writing. It uses special techniques like cutting off parts from certain characters called tokens (words) while still keeping all other ones intact. These technical improvements help make better word alignment processes even after they have been translated correctly.

Problems solved by technology

Technological Problem addressed in this patents relates to finding consistently aligned phrases within a dataset containing both Japanese Language Languages and Mandarin Germanic dictionaries during learning translating systems. Current solutions involve manually aligning documents together correctly but they often require extensive effort due to variations across languages. Therefore, technical problem solved through automatic speech recognition techniques has emerged where machines automatically identify corresponding phrase boundaries without human input while maintaining high accuracy.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Participle-network-based word alignment fusion method for computer-aided Chinese-to-English translation
  • Participle-network-based word alignment fusion method for computer-aided Chinese-to-English translation
  • Participle-network-based word alignment fusion method for computer-aided Chinese-to-English translation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0070] Algorithms used in the present invention are all written and realized by C# language. The model used in the experiment is: Intel Xeon X5550 processor, the main frequency is 2.66G HZ, and the memory is 16G. The GIZA++ word alignment toolkit used in the present invention is a general open source word alignment toolkit at present, compiled by this laboratory under Cygwin to obtain a version that can finally run under the windows platform. The rest of the machine translation modules used in the present invention are rewritten in C# language based on the phrase-based statistical machine translation open source software Moses.

[0071] The data preparation before implementation is as follows: use K kinds of word segmentation tools to segment the Chinese part of the English-Chinese parallel corpus, and get K middle word segmentation, that is, s k (k=1,...,K), put s k (k=1,...,K) do traditional word alignment with the parallel English part a k (k=1, . . . , K).

[0072] More s

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a participle-network-based word alignment fusion method for computer-aided Chinese-to-English translation. The method comprises the following steps of: 1, determining skeleton alignment: searching and selecting an optimal skeleton connection by using a connection-confidence-based connection selection algorithm, and forming the skeleton alignment; and 2, projecting the selected skeleton alignment to each participle to obtain various-participle-based word alignment. By the method, the conventional single-participle-based word alignment algorithm is improved, and the word alignment quality of each participle and the machine translation quality can be simultaneously improved. By fusing the characteristics for the word alignment under multiple participles, the final word alignment is more robust, and the number of word alignment errors affected by participle errors or bilingual participle inconsistency can be reduced.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap